KVM: X86: Provide a capability to disable HLT intercepts

If host CPUs are dedicated to a VM, we can avoid VM exits on HLT.
This patch adds the per-VM capability to disable them.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Jan H. Schönherr <jschoenh@amazon.de>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virtual/kvm/api.txt

@@ -4367,6 +4367,7 @@ Returns: 0 on success, -EINVAL when args[0] contains invalid exits
 Valid bits in args[0] are
 
 #define KVM_X86_DISABLE_EXITS_MWAIT            (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HLT              (1 << 1)
 
 Enabling this capability on a VM provides userspace with a way to no
 longer intercept some instructions for improved latency in some
@@ -4375,6 +4376,7 @@ physical CPUs.  More bits can be added in the future; userspace can
 just pass the KVM_CHECK_EXTENSION result to KVM_ENABLE_CAP to disable
 all such vmexits.
 
+Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
 
 8. Other capabilities.
 ----------------------

arch/x86/include/asm/kvm_host.h

@@ -812,6 +812,7 @@ struct kvm_arch {
 	gpa_t wall_clock;
 
 	bool mwait_in_guest;
+	bool hlt_in_guest;
 
 	bool ept_identity_pagetable_done;
 	gpa_t ept_identity_map_addr;

arch/x86/kvm/cpuid.c

@@ -135,6 +135,11 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 			return -EINVAL;
 	}
 
+	best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+	if (kvm_hlt_in_guest(vcpu->kvm) && best &&
+		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
+		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
+
 	/* Update physical-address width */
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
 	kvm_mmu_reset_context(vcpu);

arch/x86/kvm/svm.c

@@ -1380,7 +1380,6 @@ static void init_vmcb(struct vcpu_svm *svm)
 	set_intercept(svm, INTERCEPT_RDPMC);
 	set_intercept(svm, INTERCEPT_CPUID);
 	set_intercept(svm, INTERCEPT_INVD);
-	set_intercept(svm, INTERCEPT_HLT);
 	set_intercept(svm, INTERCEPT_INVLPG);
 	set_intercept(svm, INTERCEPT_INVLPGA);
 	set_intercept(svm, INTERCEPT_IOIO_PROT);
@@ -1403,6 +1402,9 @@ static void init_vmcb(struct vcpu_svm *svm)
 		set_intercept(svm, INTERCEPT_MWAIT);
 	}
 
+	if (!kvm_hlt_in_guest(svm->vcpu.kvm))
+		set_intercept(svm, INTERCEPT_HLT);
+
 	control->iopm_base_pa = __sme_set(iopm_base);
 	control->msrpm_base_pa = __sme_set(__pa(svm->msrpm));
 	control->int_ctl = V_INTR_MASKING_MASK;

arch/x86/kvm/vmx.c

@@ -2556,6 +2556,19 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit
 	return 0;
 }
 
+static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Ensure that we clear the HLT state in the VMCS.  We don't need to
+	 * explicitly skip the instruction because if the HLT state is set,
+	 * then the instruction is already executing and RIP has already been
+	 * advanced.
+	 */
+	if (kvm_hlt_in_guest(vcpu->kvm) &&
+			vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT)
+		vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
+}
+
 static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -2586,6 +2599,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 		intr_info |= INTR_TYPE_HARD_EXCEPTION;
 
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
+
+	vmx_clear_hlt(vcpu);
 }
 
 static bool vmx_rdtscp_supported(void)
@@ -5545,6 +5560,8 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
 	if (kvm_mwait_in_guest(vmx->vcpu.kvm))
 		exec_control &= ~(CPU_BASED_MWAIT_EXITING |
 				CPU_BASED_MONITOR_EXITING);
+	if (kvm_hlt_in_guest(vmx->vcpu.kvm))
+		exec_control &= ~CPU_BASED_HLT_EXITING;
 	return exec_control;
 }
 
@@ -5906,6 +5923,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	update_exception_bitmap(vcpu);
 
 	vpid_sync_context(vmx->vpid);
+	if (init_event)
+		vmx_clear_hlt(vcpu);
 }
 
 /*
@@ -5976,6 +5995,8 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu)
 	} else
 		intr |= INTR_TYPE_EXT_INTR;
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr);
+
+	vmx_clear_hlt(vcpu);
 }
 
 static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
@@ -6006,6 +6027,8 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
 
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
 			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR);
+
+	vmx_clear_hlt(vcpu);
 }
 
 static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
@@ -12347,6 +12370,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 
 	vmx->nested.smm.vmxon = vmx->nested.vmxon;
 	vmx->nested.vmxon = false;
+	vmx_clear_hlt(vcpu);
 	return 0;
 }
 

arch/x86/kvm/x86.c

@@ -2878,6 +2878,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_CLOCK_TSC_STABLE;
 		break;
 	case KVM_CAP_X86_DISABLE_EXITS:
+		r |=  KVM_X86_DISABLE_EXITS_HTL;
 		if(kvm_can_mwait_in_guest())
 			r |= KVM_X86_DISABLE_EXITS_MWAIT;
 		break;
@@ -4232,6 +4233,8 @@ split_irqchip_unlock:
 		if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) &&
 			kvm_can_mwait_in_guest())
 			kvm->arch.mwait_in_guest = true;
+		if (cap->args[0] & KVM_X86_DISABLE_EXITS_HTL)
+			kvm->arch.hlt_in_guest = true;
 		r = 0;
 		break;
 	default:

arch/x86/kvm/x86.h

@@ -265,11 +265,18 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
 	 })
 
 #define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
-#define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT)
+#define KVM_X86_DISABLE_EXITS_HTL            (1 << 1)
+#define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
+                                              KVM_X86_DISABLE_EXITS_HTL)
 
 static inline bool kvm_mwait_in_guest(struct kvm *kvm)
 {
 	return kvm->arch.mwait_in_guest;
 }
 
+static inline bool kvm_hlt_in_guest(struct kvm *kvm)
+{
+	return kvm->arch.hlt_in_guest;
+}
+
 #endif